AWS claims 40% faster AI recommendations in Milan

AWS brought EC2 R8i and R8i-Flex instances to Milan with a vendor-claimed 40% speedup for AI deep-learning recommendation models over R7i. The regional launch announcement also claims 15% better price-performance and 2.5 times the memory bandwidth of the previous Intel generation. For European inference teams watching Amazon spend $220 billion to expand cloud capacity, the useful signal is availability, not proof: benchmark the recommender’s real latency and cost before exchanging an R7i commitment for the newer shape.